Job Description

Position Overview

• Location Type: Not Specified
• Employment Type: Full Time
• Job Type: Not Specified

NVIDIA is expanding its Datacenter business, and this role is central to optimizing datacenter deployments and establishing a data-driven approach to hardware design and software development. The team collaborates with various NVIDIA teams, including DL research, CUDA Kernel, and DL Framework development, as well as Silicon Architecture teams. This role focuses on understanding the relationships between CPU, GPU, networking, and I/O in the context of deep learning architectures for applications like Natural Language Processing, Computer Vision, and Autonomous Driving. The goal is to optimize next-generation systems and the Deep Learning Software Stack.

Responsibilities

• Help develop software infrastructure to characterize and analyze a broad range of Deep Learning applications.
• Evolve cost-efficient datacenter architectures tailored to meet the needs of Large Language Models (LLMs).
• Work with experts to develop analysis and profiling tools in Python, bash, and C/C++ to measure key performance metrics of DL workloads running on Nvidia systems.
• Analyze system and software characteristics of DL applications.
• Develop analysis tools and methodologies to measure key performance metrics and to estimate potential for efficiency improvement.

Requirements

• A Bachelor’s degree in Electrical Engineering or Computer Science with 3+ years of relevant experience (Master’s or PhD degree preferred).
• Experience in at least one of the following:
  • System Software: Operating Systems (Linux), Compilers, GPU Kernels (CUDA), DL Frameworks (PyTorch, TensorFlow).
  • Silicon Architecture and Performance Modeling/Analysis: CPU, GPU, Memory, or Network Architecture
• Programming experience in C/C++ and Python.
• Exposure to Containerization Platforms (Docker) and Datacenter Workload Managers (Slurm) is a plus.
• Demonstrated ability to work in virtual environments and a strong drive to own tasks from beginning to end.

Ways to Stand Out

• Background with system software, operating system intrinsics, GPU kernels (CUDA), or DL Frameworks (PyTorch, TensorFlow).
• Experience with silicon performance monitoring or profiling tools (e.g., perf, gprof, nvidia-smi, dcgm).
• In-depth performance modeling experience in any one of CPU, GPU, Memory, or Network Architecture.
• Exposure to Containerization Platforms (Docker) and Datacenter Workload Managers (Slurm).
• Prior experience with multi-site teams or multi-functional teams.

Company Information

NVIDIA is widely considered to be one of the... (Information incomplete)